We extend a standard for doing agile scrum teamwork in education that permits individual assessment within teams (IAFOR ECE2020). Since the teacher's bandwidth in education is limited and increasingly under pressure, we focus on course design options that can be used to leverage the bandwidth. One economizing option in courses is to let teams prerecord prototype presentation videos before sprint review takes place. This allocates expensive teacher's time to team interrogation time which enriches interaction and engagement and enables effective sharing between teams to improve communication flow in sparse stakeholder feedback scenarios. We also describe three learning analytic pathways that can be smartly integrated into learning dashboards to monitor student and team progress or into learning recommender systems and chatbots to generate action-directed, just-in-time feedback and advice to students. The first one is for setup that enables control of important team diversity and student inclusion parameters such as demographic, personality and professional traits that are known from the student population in advance and that enables handy attribution of 21st-century skill sets within teams. The second one is the product pathway that builds on a datastream generated from qualitative, quantitative and immersive product features that are known from prototyping. The third one is the process pathway in which information on 21st-century skills is generated that are at play in individual and dynamic team processes. We are convinced that these extensions will further enable effective learning technology that is directed to applying agile scrum in education efficently, both for students as teachers.
Machine learning models have proven to be reliable methods in classification tasks. However, little research has been done on classifying dwelling characteristics based on smart meter & weather data before. Gaining insights into dwelling characteristics can be helpful to create/improve the policies for creating new dwellings at NZEB standard. This paper compares the different machine learning algorithms and the methods used to correctly implement the models. These methods include the data pre-processing, model validation and evaluation. Smart meter data was provided by Groene Mient, which was used to train several machine learning algorithms. The models that were generated by the algorithms were compared on their performance. The results showed that Recurrent Neural Network (RNN) 2performed the best with 96% of accuracy. Cross Validation was used to validate the models, where 80% of the data was used for training purposes and 20% was used for testing purposes. Evaluation metrices were used to produce classification reports, which can indicate which of the models work the best for this specific problem. The models were programmed in Python.
Formative assessment (FA) is an effective educational approach for optimising student learning and is considered as a promising avenue for assessment within physical education (PE). Nevertheless, implementing FA is a complex and demanding task for in-service PE teachers who often lack formal training on this topic. To better support PE teachers in implementing FA into their practice, we need better insight into teachers’ experiences while designing and implementing formative strategies. However, knowledge on this topic is limited, especially within PE. Therefore, this study examined the experiences of 15 PE teachers who participated in an 18-month professional development programme. Teachers designed and implemented various formative activities within their PE lessons, while experiences were investigated through logbook entries and focus groups. Findings indicated various positive experiences, such as increased transparency in learning outcomes and success criteria for students as well as increased student involvement, but also revealed complexities, such as shifting teacher roles and insufficient feedback literacy among students. Overall, the findings of this study underscore the importance of a sustained, collaborative, and supported approach to implementing FA.
